Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It says 'returns' and 'discover', implying a read-only operation, but doesn't explicitly state safety, latency, or any potential side effects. The phrase 'as reported by the device build' hints at a remote query but omits details like authentication requirements or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose and usage. Every word earns its place—no filler, and the critical call-before-run_task advice is placed at the end for emphasis.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple discovery tool with one optional parameter and no output schema, the description covers what it returns, when to use it, and why. It could mention potential errors or the format of the manifest in more detail, but it's adequate for an agent to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the 'device' parameter is fully described in the schema ('name or sid from list_devices. Omit only when the account has exactly one device.'). The description adds no additional parameter context, so it meets the baseline but adds no value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Discover', 'returns') and resource ('task manifest'), and explicitly distinguishes its role from run_task by describing it as a discovery step. The purpose is unambiguous and distinct from siblings like list_devices and run_task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance: 'Call this before run_task when unsure which task types exist.' This tells the agent the exact trigger condition and references the relevant sibling, making the decision tree clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.